Speech enhancement by combination of transient emphasis and noise cancelation

Daniel M. Rasetshwane, J. R. Boston, John D. Durrant, Sungyub D. Yoo, Ching Chung Li, Susan Shaiman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

This paper evaluates the effectiveness of combining speech modification techniques that enhance transition components with active noise cancellation to improve the intelligibility of speech in noise. Two speech modification techniques were considered. One is based on wavelet-packet analysis, and the second uses a fixed filter, derived from time-frequency analysis, that emphasizes high frequencies. Active noise cancellation was provided by Bose noise-cancelling headphones. The test noise was real, generated by a ground auxiliary generator on the tarmac at an Air National Guard facility. The test signals were speech tokens from the modified rhyme (psycho-acoustic) test, recorded by a male speaker. This paradigm was used to measure word recognition rates at various signal-to-noise ratios. Active noise cancellation by itself provided over 40% increase in word recognition, while the modified speech and fixed filter techniques alone provided up to 20% improvement, depending on the signal-to-noise ratio. In combination, the speech modification approaches provided over 15% additional improvement in intelligibility over noise cancellation alone.

Original languageEnglish (US)
Title of host publication2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings
Pages116-121
Number of pages6
DOIs
StatePublished - Apr 21 2011
Event2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Sedona, AZ, United States
Duration: Jan 4 2011Jan 7 2011

Publication series

Name2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings

Other

Other2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011
CountryUnited States
CitySedona, AZ
Period1/4/111/7/11

Fingerprint

Speech enhancement
Signal to noise ratio
Headphones
Speech intelligibility
frequency analysis
acoustics
Acoustics
air
paradigm
Air

Keywords

  • digital filters
  • speech enhancement
  • speech intelligibility
  • wavelet transforms

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing
  • Education

Cite this

Rasetshwane, D. M., Boston, J. R., Durrant, J. D., Yoo, S. D., Li, C. C., & Shaiman, S. (2011). Speech enhancement by combination of transient emphasis and noise cancelation. In 2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings (pp. 116-121). [5739197] (2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings). https://doi.org/10.1109/DSP-SPE.2011.5739197

Speech enhancement by combination of transient emphasis and noise cancelation. / Rasetshwane, Daniel M.; Boston, J. R.; Durrant, John D.; Yoo, Sungyub D.; Li, Ching Chung; Shaiman, Susan.

2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings. 2011. p. 116-121 5739197 (2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Rasetshwane, DM, Boston, JR, Durrant, JD, Yoo, SD, Li, CC & Shaiman, S 2011, Speech enhancement by combination of transient emphasis and noise cancelation. in 2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings., 5739197, 2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings, pp. 116-121, 2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011, Sedona, AZ, United States, 1/4/11. https://doi.org/10.1109/DSP-SPE.2011.5739197
Rasetshwane DM, Boston JR, Durrant JD, Yoo SD, Li CC, Shaiman S. Speech enhancement by combination of transient emphasis and noise cancelation. In 2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings. 2011. p. 116-121. 5739197. (2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings). https://doi.org/10.1109/DSP-SPE.2011.5739197
Rasetshwane, Daniel M. ; Boston, J. R. ; Durrant, John D. ; Yoo, Sungyub D. ; Li, Ching Chung ; Shaiman, Susan. / Speech enhancement by combination of transient emphasis and noise cancelation. 2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings. 2011. pp. 116-121 (2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings).
@inproceedings{604fbd722d9e40fe9d868e15717dd5dc,
title = "Speech enhancement by combination of transient emphasis and noise cancelation",
abstract = "This paper evaluates the effectiveness of combining speech modification techniques that enhance transition components with active noise cancellation to improve the intelligibility of speech in noise. Two speech modification techniques were considered. One is based on wavelet-packet analysis, and the second uses a fixed filter, derived from time-frequency analysis, that emphasizes high frequencies. Active noise cancellation was provided by Bose noise-cancelling headphones. The test noise was real, generated by a ground auxiliary generator on the tarmac at an Air National Guard facility. The test signals were speech tokens from the modified rhyme (psycho-acoustic) test, recorded by a male speaker. This paradigm was used to measure word recognition rates at various signal-to-noise ratios. Active noise cancellation by itself provided over 40{\%} increase in word recognition, while the modified speech and fixed filter techniques alone provided up to 20{\%} improvement, depending on the signal-to-noise ratio. In combination, the speech modification approaches provided over 15{\%} additional improvement in intelligibility over noise cancellation alone.",
keywords = "digital filters, speech enhancement, speech intelligibility, wavelet transforms",
author = "Rasetshwane, {Daniel M.} and Boston, {J. R.} and Durrant, {John D.} and Yoo, {Sungyub D.} and Li, {Ching Chung} and Susan Shaiman",
year = "2011",
month = "4",
day = "21",
doi = "10.1109/DSP-SPE.2011.5739197",
language = "English (US)",
isbn = "9781612842271",
series = "2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings",
pages = "116--121",
booktitle = "2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings",

}

TY - GEN

T1 - Speech enhancement by combination of transient emphasis and noise cancelation

AU - Rasetshwane, Daniel M.

AU - Boston, J. R.

AU - Durrant, John D.

AU - Yoo, Sungyub D.

AU - Li, Ching Chung

AU - Shaiman, Susan

PY - 2011/4/21

Y1 - 2011/4/21

N2 - This paper evaluates the effectiveness of combining speech modification techniques that enhance transition components with active noise cancellation to improve the intelligibility of speech in noise. Two speech modification techniques were considered. One is based on wavelet-packet analysis, and the second uses a fixed filter, derived from time-frequency analysis, that emphasizes high frequencies. Active noise cancellation was provided by Bose noise-cancelling headphones. The test noise was real, generated by a ground auxiliary generator on the tarmac at an Air National Guard facility. The test signals were speech tokens from the modified rhyme (psycho-acoustic) test, recorded by a male speaker. This paradigm was used to measure word recognition rates at various signal-to-noise ratios. Active noise cancellation by itself provided over 40% increase in word recognition, while the modified speech and fixed filter techniques alone provided up to 20% improvement, depending on the signal-to-noise ratio. In combination, the speech modification approaches provided over 15% additional improvement in intelligibility over noise cancellation alone.

AB - This paper evaluates the effectiveness of combining speech modification techniques that enhance transition components with active noise cancellation to improve the intelligibility of speech in noise. Two speech modification techniques were considered. One is based on wavelet-packet analysis, and the second uses a fixed filter, derived from time-frequency analysis, that emphasizes high frequencies. Active noise cancellation was provided by Bose noise-cancelling headphones. The test noise was real, generated by a ground auxiliary generator on the tarmac at an Air National Guard facility. The test signals were speech tokens from the modified rhyme (psycho-acoustic) test, recorded by a male speaker. This paradigm was used to measure word recognition rates at various signal-to-noise ratios. Active noise cancellation by itself provided over 40% increase in word recognition, while the modified speech and fixed filter techniques alone provided up to 20% improvement, depending on the signal-to-noise ratio. In combination, the speech modification approaches provided over 15% additional improvement in intelligibility over noise cancellation alone.

KW - digital filters

KW - speech enhancement

KW - speech intelligibility

KW - wavelet transforms

UR - http://www.scopus.com/inward/record.url?scp=79954497336&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79954497336&partnerID=8YFLogxK

U2 - 10.1109/DSP-SPE.2011.5739197

DO - 10.1109/DSP-SPE.2011.5739197

M3 - Conference contribution

AN - SCOPUS:79954497336

SN - 9781612842271

T3 - 2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings

SP - 116

EP - 121

BT - 2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings

ER -